检索结果-内蒙古大学图书馆

International Conference on Information Science and Communications Technologies (ICISCT)

作者： Khurshedjon Farkhodov Jin-Hyeok Park Suk-Hwan Lee Ki-Ryong Kwon Dept. of Artificial Intelligence Convergence Pukyong National Univercity Busan South Korea Dept. of IT Convergence and Application Engineering Pukyong National University Busan South Korea Dept. of Computer Engineering Donga University Busan South Korea

The current research field of object tracking has become noticeably popular among researchers where AI techniques take place with high-level accuracy. An algorithm with multifunctional abilities had proposed in different proposals in recent years. We proposed a tracking technique integrated with a virtual reality simulator – the AirSim (Areal Informatics and Robotics Simulation) City Environ model using one of the DRL models to control with a drone agent to examine a realistic environment. Additionally, the suggested method had tested via the two public: VisDrone2019 and OTB-100 datasets to compare with conventional strategies to show better performance among recent works.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Industrial IoT Smart Manufacturing Systems based on Cloud Computing Energy Efficiency Analysis using Machine Learning Algorithms

Industrial IoT Smart Manufacturing Systems based on Cloud Co...

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： P. Chinnasamy Patan Feridoz Khan C Sasikala Mavalluru Swathi M Prema Kumar Ajay Kumar Yadav Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Tamilnadu India Department of Computer Science and Engineering School of Computing Mohan Babu University Tirupati Andhra Pradesh India Dept of CSE Srinivasa Ramanujan Institute of Technology (Autonomous) Ananthapuramu Andhra Pradesh India Audisankara College of Engineering and Technology Andhra Pradesh India Dept. of ECE Shri Vishnu Engineering College for Women (A) Bhimavaram Andhra Pradesh India Department of Computer Application United Institute of Management Prayagraj India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

With open connectivity and emergent computing, the Industrial Internet of Things (IIoT) combined with cloud computing resources provides significant breakthroughs in the field of industrial automation. These developments lead to the evolution of supplemental services, which improve automation in the production and industrial sectors. This research proposes novel technique in smart manufacturing system based on cloud computing with IIoT in energy efficiency using machine learning. Here the smart manufacturing process has been analysed based on IIoT with cloud computing network, where the energy efficiency is analysed using virtual machine-based reinforcement markov chain based linear regression. Experimental analysis has been carried out in terms of latency, energy efficiency, task response time, accuracy. proposed technique obtained 97% of Latency, 95% of Energy efficiency, 98% of Accuracy, 94% of Task response time.

关键词： Cloud computing Machine learning algorithms Automation Accuracy Linear regression Energy efficiency Virtual machines Time factors Industrial Internet of Things Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Analyzing and Detecting the Fake News using Machine Learning

Analyzing and Detecting the Fake News using Machine Learning

引用

IoT, Communication and Automation Technology (ICICAT), International Conference on

作者： Santosh Kumar Upadhyay Manmohan Singh Yadav Vipin Kumar Chaudhary Motashim Rasool CSE Department Ajay Kumar Garg Engineering College Ghaziabad India CSE Department Sharda University Greater Noida India CSE Department Lovely Professional University Phagwara India Dept. of Computer Application Integral University Lucknow India

ISBN: (数字)9798350368109

ISBN: (纸本)9798350368116

Fake news has grown to be a significant concern in the age of social media and online information sharing. False news detection is a difficult problem requiring a multidisciplinary approach combining natural language processing, machine learning, and social network research. This paper provides a short review of the area by classifying the research on false news identification into three categories: feature-based approaches, machine learning methods, and social network analysis methods. Further, we have applied machine learning algorithms to identify false news. We look at various feature types used for false news identification, including textual features, metadata features, and social context features. Our proposed system performed well with a classification accuracy of 99.70%. Furthermore, we delineate prospective remedies for the issues and constraints of existing fake news detection methods.

关键词： Machine learning algorithms Accuracy Social networking (online) Reviews Information sharing Metadata Natural language processing Internet of Things Fake news Random forests

来源：评论

学校读者我要写书评

暂无评论

FedERA: Framework for Federated Learning with Diversified Edge Resource Allocation

FedERA: Framework for Federated Learning with Diversified Ed...

引用

Federated Learning Technologies and applications (FLTA), International Conference on

作者： Anupam Borthakur Aditya Kasliwal Asim Manna Dipyan Dewan Debdoot Sheet Centre of Excellence in Artificial Intelligence Indian Institute of Technology Kharagpur West Bengal India Dept. of Data Science and Computer Application Manipal Institute of Technology Manipal Karnataka India Department of Electrical Engineering Indian Institute of Technology Kharagpur West Bengal India

ISBN: (数字)9798350354812

ISBN: (纸本)9798350354829

Federated Learning (FL) is a distributed machine learning (ML) approach that allows multiple devices to train a model while keeping training data private on edge devices. However, existing FL libraries are incapable of: (i) su pporting a wide range of existing FL algorithms, (ii) handling diverse public as well as custom datasets, (iii) discarding unreliable updates from malicious edge devices, (iv) facilitating edge-device training, and (v) implementing model compression to reduce communication overhead. With the rapid progression in AI, there is an increment in the computation power while training the models on edge devices which results in more carbon emission (CE). However, in most of the existing FL frameworks, there is no module for estimating CE. In this paper, we present FedERA, a modular and fully customizable open-source FL framework aiming to address these issues especially also by offering extensive support on heterogeneous edge devices and by incorporating both standalone and distributed training approaches. The integration of new software modules unforeseen in existing FL frameworks not only amplifies the scope of its usability but also fosters environment-friendly FL. We believe that FedERA will be a valuable tool for researchers and practitioners working in FL.

关键词： Training Federated learning Operating systems Computational modeling Training data Carbon dioxide Real-time systems Software Security Usability

来源：评论

学校读者我要写书评

暂无评论

An Effective Classification of Ddos Cloud Based Attack Through Tree Founded Classifiers

An Effective Classification of Ddos Cloud Based Attack Throu...

引用

Innovations in High Speed Communication and Signal Processing (IHCSP), International Conference on

作者： Vikas Goel Pragati Goel Raju Ranjan Amit Kumar Sharma Dept. of IT KIET Group of Institutions Delhi-NCR Ghaziabad India Dept. of Computer Application NCRD'S Sterling Institute of Management Studies Nerul Navi Mumbai India School of Computing Science & Engineering Galgotia University Greater Noida India Dept. of CS&E Ch. Charan Singh University Campus Meerut India

The term “cloud computing” refers to a relatively new technology that provides users with access to various computing services and resources, including software, data storage, and communication infrastructure. There are currently certain security concerns with cloud computing. An Intrusion Detection System (IDS) is a form of network security that monitors for malicious activity. In the cloud, an IDS might operate on individual hosts or over an entire network. DoS attacks, which aim to disrupt, disable, or otherwise harm a service, have become increasingly common against cloud applications and internet services. Due to the cloud's complexity and decentralized nature, it is difficult to detect attacks on its infrastructures. Moreover, by allowing a wide variety of smart devices to access cloud-based infrastructures, it raises both the difficulty and the complexity of assaults. A decision tree is a method of categorization used in data mining. It is recommended to utilize this method when developing a classification scheme from a reclassified data set. Classifiers such as the Classification and Regression Tree (CART), C4.5, and the Random Tree (RT) are proposed in this work. The utilized CART method has a tendency to generate additional trees on nodes, until no tree can be formed judging whether or not a node is terminal. Because of its adaptability, the CART technique can handle gaps in the data. The tree is pruned to make it smaller and more manageable in C4.5. A classifier's complexity is decreased while its prediction accuracy is improved. Decision trees were used to generate the chain of basic decisions used in RT's label assignment process.

关键词： computers Cloud computing Technological innovation Web and internet services Intrusion detection Signal processing Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Regional Vegetation Cover Prediction Using Spatial Image Features and Semantic Segmentation

SSRN

引用

SSRN 2022年

作者： Chirkhare, Ganesh Hablani, Ramchand Balamwar, Sanjay Dept. of Computer Science and Engg. Shri Ramdeobaba College of Engineering & Management Nagpur440013 India Maharashtra Remote Sensing Application Centre Nagpur440011 India

Vegetation indices play a vital role in monitoring dissimilarity in vegetation. This paper presents a better procedure for the purpose of analysis and representation of multi-spectral satellite images based upon Atmospherically Resistant Vegetation Index (ARVI) and U-Net. The vegetation detection methods were applied to color images which consist of R, G, B and near-infrared (NIR) bands. Common approaches usually apply the Normalized Difference Vegetation Index (NDVI) to indicate the greenery of environment. However, there are some potential errors and inaccuracies with NDVI, one of the most important imperfection is that it is incorrect for changes in solar incidence angle, this method also produces inaccurate data due to varying factors including shadowing, air moisture, and variations in the soil. It has been found that using ARVI and deep learning helps in eliminating these errors up to some extent, and correct the inaccuracies of NDVI, which results in slight improved and near accurate vegetation segmentation. This method can be utilized for prediction of vegetation in a region for the purpose of city planning and reforestation. © 2022, The Authors. All rights reserved.

关键词： Vegetation

来源：评论

学校读者我要写书评

暂无评论

EVALUATION OF PERFORMANCE OF A CI ENGINE FUELED WITH BIODIESEL PRODUCED FROM UNUSED ALGAE

Journal of Solid Waste Technology and Management

引用

Journal of Solid Waste Technology and Management 2023年第4期49卷 359-364页

作者： Karmakar, Rachan Kumar, Nitin Rajor, Anita Kundu, Krishnendu Kumar, Rajesh Gahlot, Dinesh Chaudhury, Bhaskerpratap Ragit, S.S. Kumar, Amit Gorai, Sanjoy Gangwar, Pavan SInghal, Rishabh Bhattacharya, Sourish Sharma, Rachna Savita Singh, Narpinder Kumar, Neeraj Graphic Era Deemed to be University Uttarakhand Dehradun India Dept. of Mechanical Engineering Roorkee Institute of Technology Uttarakhand Roorkee India School of Energy and Environment Thapar University Punjab Patiala India Dept. of Biofuel CSIR CMERI CoEFM Punjab Ludhiana India Dept. of Chemistry S.S.J. University Campus Almora Uttarakhand India Dept. of Physics Chandigarh Group of Colleges Punjab Jhanjheri India Dept. of Mechanical Engineering Guru Nanak Institute of Technology Maharashtra Nagpur India Dept. of Computer Application Quantum University Uttarakhand Roorkee India Dept. of Electronics and Communication Engineering IMS Engineering College U.P. Gaziabad India Dept. of Electrical Engineering COER University Uttarakhand Roorkee India Process Design and Engineering Cell Discipline CSIR Central Salt and Marine Chemicals Research Institute Gujrat Bhavnagar India Dept. of Applied Science Roorkee Institute of Technology Uttarakhand Roorkee India School of Agriculture Graphic Era Hill University Uttarakhand Dehradun India Dept. of Food Science and Technology Graphic Era Deemed to be University Uttarakhand Dehradun India

Abundant availability and easy culture process of algae make it a better resource than other vegetable crops for biodiesel production. The oil (with 21% FFA content) extracted from the unused, mixed culture of algae in this experiment was used to produce biodiesel by an ‘acid esterification followed by alkaline esterification’ procedure. After confirming the properties of the biodiesel to be within the limit of ASTM standard, three biodiesel blends (B10, B20 and B30) were used in an internal combustion engine (Four stroke single cylinder VCR engine) and the performance of the engine was observed at different engine loads (0%, 20%, 40%, 80%, 100%, 120%). The little higher brake specific fuel consumption (0.22kg/KWh, 0.25 kg/KWh, 0.26kg/KWh and 0.21kg/KWh respectively for B10, B20, B30 and petro-diesel at overload condition), lower brake power (3.41 kW, 3.37 kW, 3.25 kW, 3.39 kW for diesel, B10, B20 and B30 respectively for B10, B20, B30 and petro-diesel) and mechanical efficiency (63.34, 51.43%, 52.06% and 51.43% for petro-diesel, B10, B20 and B30 respectively) for biodiesel blends took place which might be the results of lower calorific value (40800 kJ/kg), higher density (875.27kg/m3) and viscosity (3.14 mm2/s) of the algal biodiesel than diesel. © 2023 Widener University School of Civil engineering. All rights reserved.

关键词： Biodiesel

来源：评论

学校读者我要写书评

暂无评论

Exploratory Data Analysis using Autoviz for Machine Learning Classification Problem

Exploratory Data Analysis using Autoviz for Machine Learning...

引用

Emerging Innovations and Advanced Computing (INNOCOMP), International Conference on

作者： Guru Prasad M S Praveen Gujjar J Arnav Kotiyal Prasanna Kumar H R Raghavendra M Devadas Afsar Jahan Department of Computer Science and Engg. Graphic Era (Deemed to be University) Dehradun India Faculty of Management Studies JAIN (Deemed-to-be University) Bengaluru India Dept. of Information Science & Engg. Visvesvaraya Technological University PESITM Shivamogga India Department of Computer Science and Engineering Gitam School of Technology Gitam University Bengaluru India Department of Computer Application Graphic Era (Deemed to be University) Dehradun India

ISBN: (数字)9798350376470

ISBN: (纸本)9798350376487

As the field of machine learning continues to advance, the importance of effective exploratory data analysis (EDA) cannot be overstated, especially in the context of classification problems. This research paper introduces an innovative and automated approach to exploratory data analysis using Autoviz, a powerful Python library designed to streamline the visualization process for machine learning datasets. The study aims to demonstrate the efficacy of Autoviz in meaningful insights, facilitating feature understanding, and supporting data preprocessing for classification tasks. Furthermore, the paper discusses how Autoviz assists in feature selection by highlighting the relevance and importance of each feature about the target variable. This feature-centric analysis contributes to optimizing machine learning models by guiding the selection of relevant input features, thereby improving model accuracy and interpretability. Autoviz is a Python library designed to automate the exploratory data analysis (EDA) process for machine learning tasks. It is specifically tailored to generate a variety of visualizations that aid in understanding the structure and characteristics of a dataset. The results indicate that Autoviz significantly reduces the time and effort required for exploratory data analysis while maintaining the quality and dept. of insights obtained. The differences between Autoviz and Pycaret is discussed in this paper. It has been observed that AutoViz automates the process of exploring and analyzing data, while PyCaret is designed for the comparison, construction, and tuning of machine learning models.

关键词： Analytical models Technological innovation Data analysis Navigation Data visualization Machine learning Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Securing IoT-Edge Networks: Federated Deep Learning for Botnet Detection

Securing IoT-Edge Networks: Federated Deep Learning for Botn...

引用

International conference of Electronics, Communication and Aerospace Technology (ICECA)

作者： S. Nagasundaram R. Sindhuja B. Rajesh Kanna S. Rajalakshmi Shobana G Aviral Srivastava Department of Computer Application Vels Institute of Science Technology and advanced Studies Pallavaram Chennai Department of Medical Electronics Saveetha Engineering college Dept. of Electronics and Communication Engineering Alagappa Chettiar College of Engineering and Technology Karaikudi Department of Electronics and Communication Engineering RMK College of Engineering and Technology Department of Computer Applications College of Science and Humanities SRM Institute of Science and Technology Kattankulathur India Department of CSE Amity University Jaipur Rajasthan

Governments throughout the world are encouraging the use of “smart city” technologies to improve urban residents' day-to-day experiences. In order to improve services like healthcare, electricity distribution, water purification, traffic management, etc., smart cities implement internet-connected technologies. The proliferation of connected gadgets has led to an increase in botnet assaults based on the IoT. The term IoT is used to describe a system of computers that are linked together that may be used for a wide variety of tasks, from environmental monitoring to on-demand power switching and beyond. Many Internets of Things gadgets are inherently disparate, update at irregular intervals, and hide in plain sight on a private or company network. The safety and confidentiality issues surrounding the Internet of Things that need to be addressed in both academic and practical settings. This research study proposes a federated-based solution to botnet attack detection utilizing on-device decentralized traffic data and a deep learning (DL) model. The proposed federated method addresses privacy concerns by preventing data from leaving the network's edge on the device. Instead, the edge layer is used to do the DL calculation, which has the extra benefit of being closer to the source of the data. Many tests are run on newly made public test data sets for deep learning models. Additionally, the sets of data are presented for examination and understanding. The recommended DL model achieved better results than the ML models. Finally, this research shows that the suggested model can detect anomalies with a precision of up to 98%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pinching Antennas: Principles, applications and Challenges

arXiv

引用

arXiv 2025年

作者： Yang, Zheng Wang, Ning Sun, Yanshi Ding, Zhiguo Schober, Robert Karagiannidis, George K. Wong, Vincent W.S. Dobre, Octavia A. Fujian Provincial Engineering Technology Research Center of Photoelectric Sensing Application Fujian Normal University Fuzhou350117 China School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Khalifa University Abu Dhabi United Arab Emirates University of Manchester ManchesterM1 9BB United Kingdom Germany Group Electrical & Computer Engineering Dept. Aristotle University of Thessaloniki Thessaloniki54 124 Greece Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada Department of Electrical and Computer Engineering Memorial University St. John’sNL Canada

Flexible-antenna systems, such as fluid antennas and movable antennas, have been recognized as key enabling technologies for sixth-generation (6G) wireless networks, as they can intelligently reconfigure the effective channel gains of the users and hence significantly improve their data transmission capabilities. However, existing flexible-antenna systems have been designed to combat small-scale fading in non-line-of-sight (NLoS) conditions. As a result, they lack the ability to establish line-of-sight links, which are typically 100 times stronger than NLoS links. In addition, existing flexible-antenna systems have limited flexibility, where adding/removing an antenna is not straightforward. This article introduces an innovative flexible-antenna system called pinching antennas, which are realized by applying small dielectric particles to waveguides. We first describe the basics of pinching-antenna systems and their ability to provide strong LoS links by deploying pinching antennas close to the users as well as their capability to scale up/down the antenna system. We then focus on communication scenarios with different numbers of waveguides and pinching antennas, where innovative approaches to implement multiple-input multiple-output and non-orthogonal multiple access are discussed. In addition, promising 6G-related applications of pinching antennas, including integrated sensing and communication and next-generation multiple access, are presented. Finally, important directions for future research, such as waveguide deployment and channel estimation, are highlighted. Copyright © 2025, The Authors. All rights reserved.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：